//Methods
/// <summary>
/// Prepares a set of filters for the input data standardization.
/// </summary>
/// <param name="bundle">A bundle of the input and output data vectors.</param>
protected FeatureFilterBase[] PrepareInputFeatureFilters(VectorBundle bundle)
{
//Allocation of the feature filters
FeatureFilterBase[] inputFeatureFilters = new FeatureFilterBase[bundle.InputVectorCollection[0].Length];
for (int i = 0; i < inputFeatureFilters.Length; i++)
{
//Input data is always considered as the real numbers.
inputFeatureFilters[i] = new RealFeatureFilter(Interval.IntN1P1, //Data to be standardized between -1 and 1
new RealFeatureFilterSettings(true, //We want to standardize data
true //We want to keep a range reserve for unseen data
)
);
}
//Update feature filters
foreach (double[] vector in bundle.InputVectorCollection)
{
for (int i = 0; i < vector.Length; i++)
{
//Update filter by the next known data value.
inputFeatureFilters[i].Update(vector[i]);
}
}
return(inputFeatureFilters);
}
//Methods
public void Run()
{
//Filter test
RealFeatureFilter rff = new RealFeatureFilter(new Interval(-1, 1));
for (int i = 1; i <= 1500; i++)
{
rff.Update(_rand.NextDouble() * _rand.Next(0, 10000));
}
double featureValue = 0.5;
double filterValue = rff.ApplyFilter(featureValue);
double reverseValue = rff.ApplyReverse(filterValue);
Console.WriteLine($"Feature: {featureValue} Filter: {filterValue} Reverse: {reverseValue}");
//Pulse generator test
BasicStat sampleStat = new BasicStat();
sampleStat.Reset();
PulseGeneratorSettings modSettings = new PulseGeneratorSettings(1, 1.5, PulseGeneratorSettings.TimingMode.Poisson);
IGenerator generator = new PulseGenerator(modSettings);
int steps = 10000;
double period = 0;
for (int i = 0; i < steps; i++)
{
++period;
double sample = generator.Next();
//Console.WriteLine(sample);
if (sample != 0)
{
sampleStat.AddSampleValue(period);
period = 0;
}
}
Console.WriteLine($"Mean: {sampleStat.ArithAvg} StdDev: {sampleStat.StdDev} Min: {sampleStat.Min} Max: {sampleStat.Max}");
Console.ReadLine();
//Random distributions test
BasicStat rStat = new BasicStat();
for (int i = 0; i < 200; i++)
{
double r = _rand.NextFilterredGaussianDouble(0.5, 1, -0.5, 1);
rStat.AddSampleValue(r);
Console.WriteLine(r);
}
Console.WriteLine($"Mean: {rStat.ArithAvg} StdDev: {rStat.StdDev} Min: {rStat.Min} Max: {rStat.Max}");
Console.ReadLine();
//Activation tests
double fadingSum = 0;
for (int i = 0; i < 1000; i++)
{
fadingSum *= (1d - 0.1);
fadingSum += 1d;
Console.WriteLine(fadingSum);
}
Console.ReadLine();
IActivationFunction testAF = ActivationFactory.Create(new SimpleIFSettings(refractoryPeriods: 0), new Random(0));
TestActivation(testAF, 100, 3.5, 10, 70);
SimpleIFSettings setup = new SimpleIFSettings();
FindAFInputBorders(ActivationFactory.Create(setup, new Random(0)),
-0.1,
20
);
//Linear algebra test
double[] flatData =
{
0.2, 5, 17.3, 1.01, 54, 7,
2.2, 5.5, 12.13, 11.57, 5.71, -85,
-70.1, 15, -18.3, 0.3, 42, -6.25,
0.042, 1, 7.75, -81.01, -21.29, 5.44,
0.1, 4, -4.3, 18.01, 7.12, -3.14,
-80.1, 24.4, 4.3, 12.03, 2.789, -13
};
Matrix testM = new Matrix(6, 6, flatData);
/*
* //Inversion test
* Matrix resultM = new Matrix(testM);
* resultM.SingleThreadInverse();
*/
/*
* //Transpose test
* Matrix resultM = testM.Transpose();
*/
/*
* //Multiply test
* Matrix resultM = Matrix.Multiply(testM, testM);
* for (int i = 0; i < resultM.NumOfRows; i++)
* {
* Console.WriteLine($"{resultM.Data[i][0]}; {resultM.Data[i][1]}; {resultM.Data[i][2]}; {resultM.Data[i][3]}; {resultM.Data[i][4]}; {resultM.Data[i][5]}");
* }
*/
;
int numOfweights = 3;
int xIdx, dIdx = 0;
double[][] data = new double[3][];
data[dIdx] = new double[numOfweights];
xIdx = -1;
data[dIdx][++xIdx] = 2;
data[dIdx][++xIdx] = 1;
data[dIdx][++xIdx] = 3;
++dIdx;
data[dIdx] = new double[numOfweights];
xIdx = -1;
data[dIdx][++xIdx] = 1;
data[dIdx][++xIdx] = 3;
data[dIdx][++xIdx] = -3;
++dIdx;
data[dIdx] = new double[numOfweights];
xIdx = -1;
data[dIdx][++xIdx] = -2;
data[dIdx][++xIdx] = 4;
data[dIdx][++xIdx] = 4;
//Matrix M = new Matrix(data, true);
//Matrix I = M.Inverse(false);
//Matrix identity = M * I; //Must lead to identity matrix
Matrix I = new Matrix(3, 3);
I.AddScalarToDiagonal(1);
Matrix X = new Matrix(I);
X.Multiply(0.1);
Matrix XT = X.Transpose();
Matrix R = XT * X;
Console.ReadLine();
///*
SimpleIFSettings settings = new SimpleIFSettings(new RandomValueSettings(15, 15),
new RandomValueSettings(0.05, 0.05),
new RandomValueSettings(5, 5),
new RandomValueSettings(20, 20),
0
);
IActivationFunction af = ActivationFactory.Create(settings, new Random(0));
//*/
TestActivation(af, 800, 0.15, 10, 600);
return;
}
/// <summary>
/// Builds trained readout layer.
/// </summary>
/// <param name="dataBundle">Collection of input predictors and associated desired output values</param>
/// <param name="predictorsMapper">Optional specific mapping of predictors to readout units</param>
/// <param name="controller">Optional external regression controller</param>
/// <returns>Results of the regression</returns>
public RegressionOverview Build(VectorBundle dataBundle,
PredictorsMapper predictorsMapper = null,
TrainedNetworkBuilder.RegressionControllerDelegate controller = null
)
{
//Basic checks
int numOfPredictors = dataBundle.InputVectorCollection[0].Length;
int numOfOutputs = dataBundle.OutputVectorCollection[0].Length;
if (numOfPredictors == 0)
{
throw new InvalidOperationException($"Number of predictors must be greater tham 0.");
}
if (numOfOutputs != Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count)
{
throw new InvalidOperationException($"Incorrect length of output vectors.");
}
//Predictors mapper (specified or default)
_predictorsMapper = predictorsMapper ?? new PredictorsMapper(numOfPredictors);
//Allocation and preparation of feature filters
//Predictors
_predictorFeatureFilterCollection = new FeatureFilterBase[numOfPredictors];
Parallel.For(0, _predictorFeatureFilterCollection.Length, nrmIdx =>
{
_predictorFeatureFilterCollection[nrmIdx] = new RealFeatureFilter(DataRange, true, true);
for (int pairIdx = 0; pairIdx < dataBundle.InputVectorCollection.Count; pairIdx++)
{
//Adjust filter
_predictorFeatureFilterCollection[nrmIdx].Update(dataBundle.InputVectorCollection[pairIdx][nrmIdx]);
}
});
//Output values
_outputFeatureFilterCollection = new FeatureFilterBase[numOfOutputs];
Parallel.For(0, _outputFeatureFilterCollection.Length, nrmIdx =>
{
_outputFeatureFilterCollection[nrmIdx] = FeatureFilterFactory.Create(DataRange, Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[nrmIdx].TaskCfg.FeatureFilterCfg);
for (int pairIdx = 0; pairIdx < dataBundle.OutputVectorCollection.Count; pairIdx++)
{
//Adjust output normalizer
_outputFeatureFilterCollection[nrmIdx].Update(dataBundle.OutputVectorCollection[pairIdx][nrmIdx]);
}
});
//Data normalization
//Allocation
double[][] normalizedPredictorsCollection = new double[dataBundle.InputVectorCollection.Count][];
double[][] normalizedIdealOutputsCollection = new double[dataBundle.OutputVectorCollection.Count][];
//Normalization
Parallel.For(0, dataBundle.InputVectorCollection.Count, pairIdx =>
{
//Predictors
double[] predictors = new double[numOfPredictors];
for (int i = 0; i < numOfPredictors; i++)
{
if (_predictorsMapper.PredictorGeneralSwitchCollection[i])
{
predictors[i] = _predictorFeatureFilterCollection[i].ApplyFilter(dataBundle.InputVectorCollection[pairIdx][i]);
}
else
{
predictors[i] = double.NaN;
}
}
normalizedPredictorsCollection[pairIdx] = predictors;
//Outputs
double[] outputs = new double[numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
outputs[i] = _outputFeatureFilterCollection[i].ApplyFilter(dataBundle.OutputVectorCollection[pairIdx][i]);
}
normalizedIdealOutputsCollection[pairIdx] = outputs;
});
//Random object initialization
Random rand = new Random(0);
//Create shuffled copy of the data
VectorBundle shuffledData = new VectorBundle(normalizedPredictorsCollection, normalizedIdealOutputsCollection);
shuffledData.Shuffle(rand);
//Building of readout units
for (int unitIdx = 0; unitIdx < Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count; unitIdx++)
{
List <double[]> idealValueCollection = new List <double[]>(shuffledData.OutputVectorCollection.Count);
//Transformation of ideal vectors to a single value vectors
foreach (double[] idealVector in shuffledData.OutputVectorCollection)
{
double[] value = new double[1];
value[0] = idealVector[unitIdx];
idealValueCollection.Add(value);
}
List <double[]> readoutUnitInputVectorCollection = _predictorsMapper.CreateVectorCollection(Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[unitIdx].Name, shuffledData.InputVectorCollection);
VectorBundle readoutUnitDataBundle = new VectorBundle(readoutUnitInputVectorCollection, idealValueCollection);
TrainedNetworkClusterBuilder readoutUnitBuilder = new TrainedNetworkClusterBuilder(Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[unitIdx].Name,
Settings.GetReadoutUnitNetworksCollection(unitIdx),
DataRange,
Settings.ReadoutUnitsCfg.ReadoutUnitCfgCollection[unitIdx].TaskCfg.Type == ReadoutUnit.TaskType.Classification ? BinBorder : double.NaN,
rand,
controller
);
//Register notification
readoutUnitBuilder.RegressionEpochDone += OnRegressionEpochDone;
//Build trained readout unit. Trained unit becomes to be the predicting cluster member
_readoutUnitCollection[unitIdx] = new ReadoutUnit(unitIdx,
readoutUnitBuilder.Build(readoutUnitDataBundle,
Settings.TestDataRatio,
Settings.Folds,
Settings.Repetitions,
new FeatureFilterBase[] { _outputFeatureFilterCollection[unitIdx] }
)
);
}//unitIdx
//Readout layer is trained and ready
Trained = true;
return(new RegressionOverview(ReadoutUnitErrStatCollection));
}
/// <summary>
/// Builds trained readout layer.
/// </summary>
/// <param name="dataBundle">The data to be used for training.</param>
/// <param name="predictorsMapper">The mapper of specific predictors to readout units (optional).</param>
/// <param name="controller">The build process controller (optional).</param>
/// <param name="randomizerSeek">Specifies the random number generator initial seek (optional). A value greater than or equal to 0 will always ensure the same initialization.</param>
/// <returns>The results of training.</returns>
public RegressionOverview Build(VectorBundle dataBundle,
PredictorsMapper predictorsMapper = null,
TNRNetBuilder.BuildControllerDelegate controller = null,
int randomizerSeek = 0
)
{
if (Trained)
{
throw new InvalidOperationException("Readout layer is already built.");
}
//Basic checks
int numOfPredictors = dataBundle.InputVectorCollection[0].Length;
int numOfOutputs = dataBundle.OutputVectorCollection[0].Length;
if (numOfPredictors == 0)
{
throw new InvalidOperationException($"Number of predictors must be greater than 0.");
}
if (numOfOutputs != ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count)
{
throw new InvalidOperationException($"Incorrect length of output vectors.");
}
//Predictors mapper (specified or default)
_predictorsMapper = predictorsMapper ?? new PredictorsMapper(numOfPredictors);
//Allocation and preparation of feature filters
//Predictors
_predictorFeatureFilterCollection = new FeatureFilterBase[numOfPredictors];
Parallel.For(0, _predictorFeatureFilterCollection.Length, nrmIdx =>
{
_predictorFeatureFilterCollection[nrmIdx] = new RealFeatureFilter(InternalDataRange, true, true);
for (int pairIdx = 0; pairIdx < dataBundle.InputVectorCollection.Count; pairIdx++)
{
//Adjust filter
_predictorFeatureFilterCollection[nrmIdx].Update(dataBundle.InputVectorCollection[pairIdx][nrmIdx]);
}
});
//Output values
_outputFeatureFilterCollection = new FeatureFilterBase[numOfOutputs];
Parallel.For(0, _outputFeatureFilterCollection.Length, nrmIdx =>
{
_outputFeatureFilterCollection[nrmIdx] = FeatureFilterFactory.Create(InternalDataRange, ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection[nrmIdx].TaskCfg.FeatureFilterCfg);
for (int pairIdx = 0; pairIdx < dataBundle.OutputVectorCollection.Count; pairIdx++)
{
//Adjust output normalizer
_outputFeatureFilterCollection[nrmIdx].Update(dataBundle.OutputVectorCollection[pairIdx][nrmIdx]);
}
});
//Data normalization
//Allocation
double[][] normalizedPredictorsCollection = new double[dataBundle.InputVectorCollection.Count][];
double[][] normalizedIdealOutputsCollection = new double[dataBundle.OutputVectorCollection.Count][];
//Normalization
Parallel.For(0, dataBundle.InputVectorCollection.Count, pairIdx =>
{
//Predictors
double[] predictors = new double[numOfPredictors];
for (int i = 0; i < numOfPredictors; i++)
{
if (_predictorsMapper.PredictorGeneralSwitchCollection[i])
{
predictors[i] = _predictorFeatureFilterCollection[i].ApplyFilter(dataBundle.InputVectorCollection[pairIdx][i]);
}
else
{
predictors[i] = double.NaN;
}
}
normalizedPredictorsCollection[pairIdx] = predictors;
//Outputs
double[] outputs = new double[numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
outputs[i] = _outputFeatureFilterCollection[i].ApplyFilter(dataBundle.OutputVectorCollection[pairIdx][i]);
}
normalizedIdealOutputsCollection[pairIdx] = outputs;
});
//Random object initialization
Random rand = (randomizerSeek < 0 ? new Random() : new Random(randomizerSeek));
//Create shuffled copy of the data
VectorBundle shuffledData = new VectorBundle(normalizedPredictorsCollection, normalizedIdealOutputsCollection);
shuffledData.Shuffle(rand);
//"One Takes All" groups input data space initialization
List <CompositeResult[]> allReadoutUnitResults = new List <CompositeResult[]>(shuffledData.InputVectorCollection.Count);
if (_oneTakesAllGroupCollection != null)
{
for (int i = 0; i < shuffledData.InputVectorCollection.Count; i++)
{
allReadoutUnitResults.Add(new CompositeResult[ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count]);
}
}
ResetProgressTracking();
//Building of readout units
for (_buildReadoutUnitIdx = 0; _buildReadoutUnitIdx < ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection.Count; _buildReadoutUnitIdx++)
{
List <double[]> idealValueCollection = new List <double[]>(shuffledData.OutputVectorCollection.Count);
//Transformation of ideal vectors to a single value vectors
foreach (double[] idealVector in shuffledData.OutputVectorCollection)
{
double[] value = new double[1];
value[0] = idealVector[_buildReadoutUnitIdx];
idealValueCollection.Add(value);
}
List <double[]> readoutUnitInputVectorCollection = _predictorsMapper.CreateVectorCollection(ReadoutLayerCfg.ReadoutUnitsCfg.ReadoutUnitCfgCollection[_buildReadoutUnitIdx].Name, shuffledData.InputVectorCollection);
VectorBundle readoutUnitDataBundle = new VectorBundle(readoutUnitInputVectorCollection, idealValueCollection);
_readoutUnitCollection[_buildReadoutUnitIdx].ReadoutUnitBuildProgressChanged += OnReadoutUnitBuildProgressChanged;
_readoutUnitCollection[_buildReadoutUnitIdx].Build(readoutUnitDataBundle,
_outputFeatureFilterCollection[_buildReadoutUnitIdx],
rand,
controller
);
//Add unit's all computed results into the input data for "One Takes All" groups
if (_oneTakesAllGroupCollection != null)
{
for (int sampleIdx = 0; sampleIdx < readoutUnitDataBundle.InputVectorCollection.Count; sampleIdx++)
{
allReadoutUnitResults[sampleIdx][_buildReadoutUnitIdx] = _readoutUnitCollection[_buildReadoutUnitIdx].Compute(readoutUnitDataBundle.InputVectorCollection[sampleIdx]);
}
}
}//unitIdx
//One Takes All groups build
if (_oneTakesAllGroupCollection != null)
{
foreach (OneTakesAllGroup group in _oneTakesAllGroupCollection)
{
//Only the group having inner probabilistic cluster has to be built
if (group.DecisionMethod == OneTakesAllGroup.OneTakesAllDecisionMethod.ClusterChain)
{
BinFeatureFilter[] groupFilters = new BinFeatureFilter[group.NumOfMemberClasses];
for (int i = 0; i < group.NumOfMemberClasses; i++)
{
groupFilters[i] = (BinFeatureFilter)_outputFeatureFilterCollection[group.MemberReadoutUnitIndexCollection[i]];
}
++_buildOTAGroupIdx;
group.OTAGBuildProgressChanged += OnOTAGBuildProgressChanged;
group.Build(allReadoutUnitResults, shuffledData.OutputVectorCollection, groupFilters, rand, controller);
}
}
}
//Readout layer is trained and ready
Trained = true;
return(new RegressionOverview(ReadoutUnitErrStatCollection));
}
/// <summary>
/// Builds readout layer.
/// Prepares prediction clusters containing trained readout units.
/// </summary>
/// <param name="dataBundle">Collection of input predictors and associated desired output values</param>
/// <param name="regressionController">Regression controller delegate</param>
/// <param name="regressionControllerData">An user object</param>
/// <param name="predictorsMapper">Optional specific mapping of predictors to readout units</param>
/// <returns>Returned ResultComparativeBundle is something like a protocol.
/// There is recorded fold by fold (unit by unit) predicted and corresponding ideal values.
/// This is the pesimistic approach. Real results on unseen data could be better due to the clustering.
/// </returns>
public ResultBundle Build(VectorBundle dataBundle,
ReadoutUnit.RegressionCallbackDelegate regressionController,
Object regressionControllerData,
PredictorsMapper predictorsMapper = null
)
{
//Basic checks
int numOfPredictors = dataBundle.InputVectorCollection[0].Length;
int numOfOutputs = dataBundle.OutputVectorCollection[0].Length;
if (numOfPredictors == 0)
{
throw new Exception("Number of predictors must be greater tham 0.");
}
if (numOfOutputs != _settings.ReadoutUnitCfgCollection.Count)
{
throw new Exception("Incorrect number of ideal output values in the vector.");
}
//Predictors mapper (specified or default)
_predictorsMapper = predictorsMapper ?? new PredictorsMapper(numOfPredictors);
//Allocation and preparation of feature filters
//Predictors
_predictorFeatureFilterCollection = new BaseFeatureFilter[numOfPredictors];
Parallel.For(0, _predictorFeatureFilterCollection.Length, nrmIdx =>
{
_predictorFeatureFilterCollection[nrmIdx] = new RealFeatureFilter(DataRange, true, true);
for (int pairIdx = 0; pairIdx < dataBundle.InputVectorCollection.Count; pairIdx++)
{
//Adjust filter
_predictorFeatureFilterCollection[nrmIdx].Update(dataBundle.InputVectorCollection[pairIdx][nrmIdx]);
}
});
//Output values
_outputFeatureFilterCollection = new BaseFeatureFilter[numOfOutputs];
Parallel.For(0, _outputFeatureFilterCollection.Length, nrmIdx =>
{
_outputFeatureFilterCollection[nrmIdx] = FeatureFilterFactory.Create(DataRange, _settings.ReadoutUnitCfgCollection[nrmIdx].FeatureFilterCfg);
for (int pairIdx = 0; pairIdx < dataBundle.OutputVectorCollection.Count; pairIdx++)
{
//Adjust output normalizer
_outputFeatureFilterCollection[nrmIdx].Update(dataBundle.OutputVectorCollection[pairIdx][nrmIdx]);
}
});
//Data normalization
//Allocation
double[][] predictorsCollection = new double[dataBundle.InputVectorCollection.Count][];
double[][] idealOutputsCollection = new double[dataBundle.OutputVectorCollection.Count][];
//Normalization
Parallel.For(0, dataBundle.InputVectorCollection.Count, pairIdx =>
{
//Predictors
double[] predictors = new double[numOfPredictors];
for (int i = 0; i < numOfPredictors; i++)
{
if (_predictorsMapper.PredictorGeneralSwitchCollection[i])
{
predictors[i] = _predictorFeatureFilterCollection[i].ApplyFilter(dataBundle.InputVectorCollection[pairIdx][i]);
}
else
{
predictors[i] = double.NaN;
}
}
predictorsCollection[pairIdx] = predictors;
//Outputs
double[] outputs = new double[numOfOutputs];
for (int i = 0; i < numOfOutputs; i++)
{
outputs[i] = _outputFeatureFilterCollection[i].ApplyFilter(dataBundle.OutputVectorCollection[pairIdx][i]);
}
idealOutputsCollection[pairIdx] = outputs;
});
//Data processing
//Random object initialization
Random rand = new Random(0);
//Allocation of computed and ideal vectors for result comparative bundle
List <double[]> validationComputedVectorCollection = new List <double[]>(idealOutputsCollection.Length);
List <double[]> validationIdealVectorCollection = new List <double[]>(idealOutputsCollection.Length);
for (int i = 0; i < idealOutputsCollection.Length; i++)
{
validationComputedVectorCollection.Add(new double[numOfOutputs]);
validationIdealVectorCollection.Add(new double[numOfOutputs]);
}
//Test dataset size
if (_settings.TestDataRatio > MaxRatioOfTestData)
{
throw new ArgumentException($"Test dataset size is greater than {MaxRatioOfTestData.ToString(CultureInfo.InvariantCulture)}", "TestDataSetSize");
}
int testDataSetLength = (int)Math.Round(idealOutputsCollection.Length * _settings.TestDataRatio, 0);
if (testDataSetLength < MinLengthOfTestDataset)
{
throw new ArgumentException($"Num of test samples is less than {MinLengthOfTestDataset.ToString(CultureInfo.InvariantCulture)}", "TestDataSetSize");
}
//Number of folds
int numOfFolds = _settings.NumOfFolds;
if (numOfFolds <= 0)
{
//Auto setup
numOfFolds = idealOutputsCollection.Length / testDataSetLength;
if (numOfFolds > MaxNumOfFolds)
{
numOfFolds = MaxNumOfFolds;
}
}
//Create shuffled copy of the data
VectorBundle shuffledData = new VectorBundle(predictorsCollection, idealOutputsCollection);
shuffledData.Shuffle(rand);
//Data inspection, preparation of datasets and training of ReadoutUnits
//Clusters of readout units (one cluster per each output field)
for (int clusterIdx = 0; clusterIdx < _settings.ReadoutUnitCfgCollection.Count; clusterIdx++)
{
_clusterCollection[clusterIdx] = new ReadoutUnit[numOfFolds];
List <double[]> idealValueCollection = new List <double[]>(idealOutputsCollection.Length);
BinDistribution refBinDistr = null;
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == ReadoutUnit.TaskType.Classification)
{
//Reference binary distribution is relevant only for classification task
refBinDistr = new BinDistribution(DataRange.Mid);
}
//Transformation to a single value vectors and data analysis
foreach (double[] idealVector in shuffledData.OutputVectorCollection)
{
double[] value = new double[1];
value[0] = idealVector[clusterIdx];
idealValueCollection.Add(value);
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == ReadoutUnit.TaskType.Classification)
{
//Reference binary distribution is relevant only for classification task
refBinDistr.Update(value);
}
}
List <VectorBundle> subBundleCollection = null;
List <double[]> readoutUnitInputVectorCollection = _predictorsMapper.CreateVectorCollection(_settings.ReadoutUnitCfgCollection[clusterIdx].Name, shuffledData.InputVectorCollection);
//Datasets preparation is depending on the task type
if (_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType == ReadoutUnit.TaskType.Classification)
{
//Classification task
subBundleCollection = DivideSamplesForClassificationTask(readoutUnitInputVectorCollection,
idealValueCollection,
refBinDistr,
testDataSetLength
);
}
else
{
//Forecast task
subBundleCollection = DivideSamplesForForecastTask(readoutUnitInputVectorCollection,
idealValueCollection,
testDataSetLength
);
}
//Find best unit per each fold in the cluster.
ClusterErrStatistics ces = new ClusterErrStatistics(_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType, numOfFolds, refBinDistr);
int arrayPos = 0;
for (int foldIdx = 0; foldIdx < numOfFolds; foldIdx++)
{
//Build training samples
List <double[]> trainingPredictorsCollection = new List <double[]>();
List <double[]> trainingIdealValueCollection = new List <double[]>();
for (int bundleIdx = 0; bundleIdx < subBundleCollection.Count; bundleIdx++)
{
if (bundleIdx != foldIdx)
{
trainingPredictorsCollection.AddRange(subBundleCollection[bundleIdx].InputVectorCollection);
trainingIdealValueCollection.AddRange(subBundleCollection[bundleIdx].OutputVectorCollection);
}
}
//Call training regression to get the best fold's readout unit.
//The best unit becomes to be the predicting cluster member.
_clusterCollection[clusterIdx][foldIdx] = ReadoutUnit.CreateTrained(_settings.ReadoutUnitCfgCollection[clusterIdx].TaskType,
clusterIdx,
foldIdx + 1,
numOfFolds,
refBinDistr,
trainingPredictorsCollection,
trainingIdealValueCollection,
subBundleCollection[foldIdx].InputVectorCollection,
subBundleCollection[foldIdx].OutputVectorCollection,
rand,
_settings.ReadoutUnitCfgCollection[clusterIdx],
regressionController,
regressionControllerData
);
//Cluster error statistics & data for validation bundle (pesimistic approach)
for (int sampleIdx = 0; sampleIdx < subBundleCollection[foldIdx].OutputVectorCollection.Count; sampleIdx++)
{
double nrmComputedValue = _clusterCollection[clusterIdx][foldIdx].Network.Compute(subBundleCollection[foldIdx].InputVectorCollection[sampleIdx])[0];
double natComputedValue = _outputFeatureFilterCollection[clusterIdx].ApplyReverse(nrmComputedValue);
double natIdealValue = _outputFeatureFilterCollection[clusterIdx].ApplyReverse(subBundleCollection[foldIdx].OutputVectorCollection[sampleIdx][0]);
ces.Update(nrmComputedValue,
subBundleCollection[foldIdx].OutputVectorCollection[sampleIdx][0],
natComputedValue,
natIdealValue);
validationIdealVectorCollection[arrayPos][clusterIdx] = natIdealValue;
validationComputedVectorCollection[arrayPos][clusterIdx] = natComputedValue;
++arrayPos;
}
} //foldIdx
_clusterErrStatisticsCollection.Add(ces);
} //clusterIdx
//Validation bundle is returned.
return(new ResultBundle(validationComputedVectorCollection, validationIdealVectorCollection));
}
